PhD student - Generative methods for synthetic data generation

The Fraunhofer Society is one of the world's leading organisations for application-oriented research. 75 institutes develop groundbreaking technologies for our economy and society – more precisely: 32 000 people from technology, science, administration and IT. You know, who comes to Fraunhofer wants and can change something. For yourself, for us and the markets of today and tomorrow. As part of »Zentrum fürgewandte Künstliche Intelligence Duisburg« (short: ZaKI.D), we want to support the regional economy in the transformation in Duisburg and adjacent regions with promising AI technologies. Together with the University of Duisburg-Essen and the KROHNE Messtechnik GmbH, we will help small and medium-sized enterprises (SMEs) from the Fraunhofer Institute for Microelectronic Circuits and Systems to integrate artificial intelligence into their businesses and products. The technological focus of the ZaKI.D is embedded artificial intelligence on resource-restricted devices such as sensors, smart devices or robots. We want to make these safer and smarter, optimize manufacturing processes, increase the quality of products and at the same time minimize the ecological footprint. Generative methods for generating synthetic data for computer vision applications are also the focus of our efforts. In the industrial environment, there is often a question of how far automated calculations can be made from 2D plans. These plans are usually created by CAD systems and exchanged via interface formats. Lack of freely available datasets can be generated for training a basic model (Foundation Model) synthetic data – at this point you will apply your three-year doctorate.

You research the research stand on Foundation Model architectures for 2D project generation from photos and the creation of offers from 2D plans You train and finetunen Foundation Models using common software libraries to improve the detection capability of an Image2Plan model The development of an adapter can help model training improve the geometric accuracy of the data. This adapter has to be developed in order to improve the pipeline for the generation of accurate synthetic plan data. In close cooperation with our experts, you implement the methods in a generative AI framework that can be used by industrial customers. You develop a test and evaluation environment for Foundation Models and provide the results of your experimental work in scientific publications or present them at international conferences and project meetings with external partners In addition, you will supervise student and scientific assistants as well as bachelor and master thesis.

Minimum qualification: Highly completed studies (M.Sc. or Uni-Diplom) in computer science, mathematics, physics, electrical engineering, mechanical engineering or a comparable technical/nature science course Good knowledge of the programming language Python and/or C++ and with relevant tools/frameworks such as CAD, bpy, Scikit-Learn, PyTorch or the like. First practical experience in the application of generic AI methods, about 3D Gaussian Splating, Neural Rendering or related processes Knowledge of the transformation of object coordinates to image coordinates A systematic and independent way of working, coupled with creativity, hands-on mentality and communication security Very good knowledge of German and English for cooperation with our project partners and for lectures at conferences Required qualifications: Master or Diploma thesis in the field of synthetic data production Practical experience in the application of AI methods in the industrial sector Practical experience in handling HPC clusters Knowledge of computer game development is advantageous, for example with C#, OpenGL or comparable technologies.

You work on pioneering topics in a redesigned team with interdisciplinary scientists in the field of machine learning and generative AI In addition to the support provided by an institute-internal specialist, a regular exchange takes place on the scientific state of your work within the framework of a doctorate/vätergremium. During the promotion period, you will be supported by accompanying offers. You will learn to safely apply professional methods of project management and to support the project acquisition. If the dissertation is submitted in due time, the option is to further deepen the research work within the framework of a connection agreement or to switch to other areas. The full-time post as a doctoral student with half-remuneration provides 50% of the time for your doctoral degree and 50% for cooperation in research projects as a scientific assistant. Flexible working hours (running time with integrated core working time from 9:30 - 15:00, Friday from 9:30 - 13:00) and mobile work on up to two days a week for better reconciliation of work and private life Occupational pension (VBL) and grant to the Deutschland-Ticket Job Very good transport with public transport/car and free parking and lockable bicycle parking for employees Family and Occupational Compatibility Support: Mit-Kind-Office, Kindernotpflege und Beratungs zu Homecare-Eldercare etc. in cooperation with the pme family service Corporate Benefits: Benefits Offers from renowned manufacturers and brands